How Lexical is Bilingual Lexicon Induction?
Harsh Kohli, Helian Feng, Nicholas Dronen, Calvin McCarter, Sina Moeini, Ali Kebarighotbi
Abstract
In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, retrieve-and-rank approach to BLI has achieved state of the art results on the task. However, the problem remains challenging in low-resource settings, due to the paucity of data. The task is complicated by factors such as lexical variation across languages. We argue that the incorporation of additional lexical information into the recent retrieve-and-rank approach should improve lexicon induction. We demonstrate the efficacy of our proposed approach on XLING, improving over the previous state of the art by an average of 2% across all language pairs.
BibTeX
@inproceedings{kohli-etal-2024-lexical,
title = "How Lexical is Bilingual Lexicon Induction?",
author = "Kohli, Harsh and
Feng, Helian and
Dronen, Nicholas and
McCarter, Calvin and
Moeini, Sina and
Kebarighotbi, Ali",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.273/",
doi = "10.18653/v1/2024.findings-naacl.273",
pages = "4381--4386"
}